Zero Slop

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With all annotation hints false, the description carries the behavioral burden and adds meaningful details: it returns the 'safest source-preserving edit', reports exact before/after scores, emits a 'clear review warning' if a target is missed, and notes result/speed variability across hosts. Some terms like 'local scoring' and 'source checks' remain under-explained, preventing a higher score.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The core behavior is front-loaded and the early sentences are fairly efficient, but the description becomes cluttered with the garbled sentence 'Try and MCP use our hosted Zero Slop agent harness' and an unexplained portability caveat. That sentence is hard to parse and reduces conciseness and readability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers main behavior, outputs, warning behavior, and ethical constraints, and an output schema exists, so it is reasonably complete for an agent selecting the tool. However, key concepts like 'writing target', 'source checks', and 'bounded response' are not defined, and the harness portability comment is ambiguously worded.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents text, genre, and audience thoroughly, including treating text as untrusted data. The description connects these parameters to outcomes like writing scores and review warnings but adds no new parameter-specific meaning beyond that, which matches the baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ('Rewrite a pasted draft') and mentions concrete outputs: one bounded AI editorial response, local scoring, source checks, before and after writing scores. It is clear what the tool does, though 'bounded' and 'source checks' are left somewhat vague and would benefit from precise definition.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear context for use: apply it to improve writing quality on a pasted draft, and it explicitly forbids using it to hide authorship or evade disclosure requirements. There are no sibling tools, so explicit alternative routing is not needed, though more detail on when not to use it operationally would strengthen this dimension.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.